{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:04:08Z","timestamp":1781885048543,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61922027, 6207115, 61932022"],"award-info":[{"award-number":["61922027, 6207115, 61932022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548394","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:43:12Z","timestamp":1665416592000},"page":"2730-2738","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation"],"prefix":"10.1145","author":[{"given":"Jialei","family":"Xu","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianming","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology & Peng Cheng Laboratory, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanchao","family":"Bai","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology & Peng Cheng Laboratory, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen DJI Sciences and Technologies Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaozhi","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen DJI Sciences and Technologies Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0902-9"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00167"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018","author":"Bhat Shariq Farooq","year":"2021","unstructured":"Shariq Farooq Bhat , Ibraheem Alhashim , and Peter Wonka . 2021 . Adabins: Depth estimation using adaptive bins . In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018 . Shariq Farooq Bhat, Ibraheem Alhashim, and Peter Wonka. 2021. Adabins: Depth estimation using adaptive bins. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4009--4018."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00271"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_6_1","volume-title":"Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems","author":"Eigen David","year":"2014","unstructured":"David Eigen , Christian Puhrsch , and Rob Fergus . 2014. Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems , Vol. 27 ( 2014 ). David Eigen, Christian Puhrsch, and Rob Fergus. 2014. Depth map prediction from a single image using a multi-scale deep network. Advances in neural information processing systems, Vol. 27 (2014)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.264"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_45"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2354409.2354978"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.699"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00393"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00257"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3150884"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2832296"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.156"},{"key":"e_1_3_2_1_19_1","volume-title":"Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes. arXiv preprint arXiv:2106.12958","author":"Keltjens Benjamin","year":"2021","unstructured":"Benjamin Keltjens , Tom van Dijk , and Guido de Croon . 2021. Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes. arXiv preprint arXiv:2106.12958 ( 2021 ). Benjamin Keltjens, Tom van Dijk, and Guido de Croon. 2021. Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes. arXiv preprint arXiv:2106.12958 (2021)."},{"key":"e_1_3_2_1_20_1","volume-title":"Learning unsupervised multi-view stereopsis via robust photometric consistency. arXiv preprint arXiv:1905.02706","author":"Khot Tejas","year":"2019","unstructured":"Tejas Khot , Shubham Agrawal , Shubham Tulsiani , Christoph Mertz , Simon Lucey , and Martial Hebert . 2019. Learning unsupervised multi-view stereopsis via robust photometric consistency. arXiv preprint arXiv:1905.02706 ( 2019 ). Tejas Khot, Shubham Agrawal, Shubham Tulsiani, Christoph Mertz, Simon Lucey, and Martial Hebert. 2019. Learning unsupervised multi-view stereopsis via robust photometric consistency. arXiv preprint arXiv:1905.02706 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00226"},{"key":"e_1_3_2_1_23_1","volume-title":"Learning depth from single monocular images using deep convolutional neural fields","author":"Liu Fayao","year":"2015","unstructured":"Fayao Liu , Chunhua Shen , Guosheng Lin , and Ian Reid . 2015. Learning depth from single monocular images using deep convolutional neural fields . IEEE transactions on pattern analysis and machine intelligence, Vol. 38 , 10 ( 2015 ), 2024--2039. Fayao Liu, Chunhua Shen, Guosheng Lin, and Ian Reid. 2015. Learning depth from single monocular images using deep convolutional neural fields. IEEE transactions on pattern analysis and machine intelligence, Vol. 38, 10 (2015), 2024--2039."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1017\/S096249291700006X"},{"key":"e_1_3_2_1_25_1","first-page":"0","volume-title":"CUP","author":"Page GF","year":"2005","unstructured":"GF Page . 2005 . MULTIPLE VIEW GEOMETRY IN COMPUTER VISION, by Richard Hartley and Andrew Zisserman , CUP , Cambridge, UK , 2003, vi 560 pp., ISBN 0 - 521 -54051-8.(Paperbackpounds 44.95). Robotica, Vol. 23, 2 (2005), 271--271. GF Page. 2005. MULTIPLE VIEW GEOMETRY IN COMPUTER VISION, by Richard Hartley and Andrew Zisserman, CUP, Cambridge, UK, 2003, vi 560 pp., ISBN 0-521-54051-8.(Paperbackpounds 44.95). Robotica, Vol. 23, 2 (2005), 271--271."},{"key":"e_1_3_2_1_26_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke , Sam Gross , Francisco Massa , Adam Lerer , James Bradbury , Gregory Chanan , Trevor Killeen , Zeming Lin , Natalia Gimelshein , Luca Antiga , 2019 . Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems , Vol. 32 (2019). Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"e_1_3_2_1_28_1","volume-title":"International journal of computer vision","author":"Scharstein Daniel","year":"2002","unstructured":"Daniel Scharstein and Richard Szeliski . 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms . International journal of computer vision , Vol. 47 , 1 ( 2002 ), 7--42. Daniel Scharstein and Richard Szeliski. 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International journal of computer vision, Vol. 47, 1 (2002), 7--42."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01413"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00216"},{"key":"e_1_3_2_1_32_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang , Alan C Bovik , Hamid R Sheikh , and Eero P Simoncelli . 2004. Image quality assessment: from error visibility to structural similarity . IEEE transactions on image processing, Vol. 13 , 4 ( 2004 ), 600--612. Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600--612."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"e_1_3_2_1_34_1","volume-title":"SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation. arXiv preprint arXiv:2204.03636","author":"Wei Yi","year":"2022","unstructured":"Yi Wei , Linqing Zhao , Wenzhao Zheng , Zheng Zhu , Yongming Rao , Guan Huang , Jiwen Lu , and Jie Zhou . 2022. SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation. arXiv preprint arXiv:2204.03636 ( 2022 ). Yi Wei, Linqing Zhao, Wenzhao Zheng, Zheng Zhu, Yongming Rao, Guan Huang, Jiwen Lu, and Jie Zhou. 2022. SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation. arXiv preprint arXiv:2204.03636 (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data. arXiv preprint arXiv:2109.11573","author":"Xu Jialei","year":"2021","unstructured":"Jialei Xu , Yuanchao Bai , Xianming Liu , Junjun Jiang , and Xiangyang Ji. 2021. Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data. arXiv preprint arXiv:2109.11573 ( 2021 ). Jialei Xu, Yuanchao Bai, Xianming Liu, Junjun Jiang, and Xiangyang Ji. 2021. Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data. arXiv preprint arXiv:2109.11573 (2021)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00493"},{"key":"e_1_3_2_1_37_1","volume-title":"Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction","author":"Yin Wei","year":"2021","unstructured":"Wei Yin , Yifan Liu , and Chunhua Shen . 2021 a. Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction . IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) ( 2021). Wei Yin, Yifan Liu, and Chunhua Shen. 2021a. Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2021)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00578"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Wei Yin Jianming Zhang Oliver Wang Simon Niklaus Long Mai Simon Chen and Chunhua Shen. 2021b. Learning to Recover 3D Scene Shape from a Single Image.  Wei Yin Jianming Zhang Oliver Wang Simon Niklaus Long Mai Simon Chen and Chunhua Shen. 2021b. Learning to Recover 3D Scene Shape from a Single Image.","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.700"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548394","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:44Z","timestamp":1750186844000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":40,"alternative-id":["10.1145\/3503161.3548394","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548394","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}